{ | |
"version": "1.0", | |
"truncation": { | |
"direction": "Right", | |
"max_length": 2048, | |
"strategy": "LongestFirst", | |
"stride": 0 | |
}, | |
"padding": { | |
"strategy": { | |
"Fixed": 2048 | |
}, | |
"direction": "Right", | |
"pad_to_multiple_of": null, | |
"pad_id": 6, | |
"pad_type_id": 0, | |
"pad_token": "[PAD]" | |
}, | |
"added_tokens": [ | |
{ | |
"id": 5, | |
"content": "[UNK]", | |
"single_word": false, | |
"lstrip": false, | |
"rstrip": false, | |
"normalized": false, | |
"special": true | |
}, | |
{ | |
"id": 6, | |
"content": "[PAD]", | |
"single_word": false, | |
"lstrip": false, | |
"rstrip": false, | |
"normalized": false, | |
"special": true | |
}, | |
{ | |
"id": 7, | |
"content": "[CLS]", | |
"single_word": false, | |
"lstrip": false, | |
"rstrip": false, | |
"normalized": false, | |
"special": true | |
}, | |
{ | |
"id": 8, | |
"content": "[SEP]", | |
"single_word": false, | |
"lstrip": false, | |
"rstrip": false, | |
"normalized": false, | |
"special": true | |
}, | |
{ | |
"id": 9, | |
"content": "[MASK]", | |
"single_word": false, | |
"lstrip": false, | |
"rstrip": false, | |
"normalized": false, | |
"special": true | |
} | |
], | |
"normalizer": null, | |
"pre_tokenizer": { | |
"type": "Split", | |
"pattern": { | |
"String": "" | |
}, | |
"behavior": "Isolated", | |
"invert": false | |
}, | |
"post_processor": null, | |
"decoder": null, | |
"model": { | |
"type": "WordLevel", | |
"vocab": { | |
"A": 0, | |
"T": 1, | |
"C": 2, | |
"G": 3, | |
"N": 4, | |
"[UNK]": 5, | |
"[PAD]": 6, | |
"[CLS]": 7, | |
"[SEP]": 8, | |
"[MASK]": 9 | |
}, | |
"unk_token": "[UNK]" | |
} | |
} |